LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

MiniMax M2.7 REAP 172B A10B BF16 by saricles

 »  All LLMs  »  saricles  »  MiniMax M2.7 REAP 172B A10B BF16   URL Share it on

  618   

MiniMax M2.7 REAP 172B A10B BF16 is an open-source language model by saricles. Features: 172b LLM, VRAM: 210GB, Context: 192K, License: other, LLM Explorer Score: 0.33.

  Arxiv:2510.13999   Agentic Base model:finetune:minimaxai/... Base model:minimaxai/minimax-m...   Bf16   Conversational   Custom code   En   Endpoints compatible   Expert-pruning   Minimax   Minimax m2   Moe   Pruned   Reap   Region:us   Safetensors   Sharded   Tensorflow   Tool-use   Zh
Model Card on HF 🤗: https://huggingface.co/saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 

MiniMax M2.7 REAP 172B A10B BF16 Benchmarks

LLME Score: 0.32587
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMax M2.7 REAP 172B A10B BF16 (saricles/MiniMax-M2.7-REAP-172B-A10B-BF16)
🌟 Advertise your project 🚀

MiniMax M2.7 REAP 172B A10B BF16 Parameters and Internals

LLM NameMiniMax M2.7 REAP 172B A10B BF16
Repository 🤗https://huggingface.co/saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 
Base Model(s)  MiniMaxAI/MiniMax-M2.7   MiniMaxAI/MiniMax-M2.7
Model Size172b
Required VRAM210 GB
Updated2026-04-18
Maintainersaricles
Model Typeminimax_m2
Model Files  5.0 GB: 1-of-70   5.0 GB: 2-of-70   5.0 GB: 3-of-70   5.0 GB: 4-of-70   5.0 GB: 5-of-70   5.0 GB: 6-of-70   5.0 GB: 7-of-70   5.0 GB: 8-of-70   5.0 GB: 9-of-70   5.0 GB: 10-of-70   5.0 GB: 11-of-70   5.0 GB: 12-of-70   5.0 GB: 13-of-70   5.0 GB: 14-of-70   5.0 GB: 15-of-70   5.0 GB: 16-of-70   5.0 GB: 17-of-70   5.0 GB: 18-of-70   5.0 GB: 19-of-70   5.0 GB: 20-of-70   5.0 GB: 21-of-70   5.0 GB: 22-of-70   5.0 GB: 23-of-70   5.0 GB: 24-of-70   5.0 GB: 25-of-70   5.0 GB: 26-of-70   5.0 GB: 27-of-70   5.0 GB: 28-of-70   5.0 GB: 29-of-70   5.0 GB: 30-of-70   5.0 GB: 31-of-70   5.0 GB: 32-of-70   5.0 GB: 33-of-70   5.0 GB: 34-of-70   5.0 GB: 35-of-70   5.0 GB: 36-of-70   5.0 GB: 37-of-70   5.0 GB: 38-of-70   5.0 GB: 39-of-70   5.0 GB: 40-of-70   5.0 GB: 41-of-70   5.0 GB: 42-of-70
Supported Languagesen zh
Model ArchitectureMiniMaxM2ForCausalLM
Licenseother
Context Length196608
Model Max Length196608
Transformers Version4.57.6
Vocabulary Size200064

Best Alternatives to MiniMax M2.7 REAP 172B A10B BF16

Best Alternatives
Context / RAM
Downloads
Likes
...M2.7 REAP 172B A10B NVFP4 GB10192K / 98.9 GB6413
...REAP 172B A10B AutoRound W4A16192K / 91.4 GB2322
Note: green Score (e.g. "73.2") means that the model is better than saricles/MiniMax-M2.7-REAP-172B-A10B-BF16.

Rank the MiniMax M2.7 REAP 172B A10B BF16 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52996 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer